ponytail
Use when building or reviewing agency's frugal discipline (Spec 332) or multi-agent self-installer (Spec 333), or when you want the minimal-code "lazy senior…
Skill by netzkontrast
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/netzkontrast-ponytail
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ponytail
What's inside
- Skill name
ponytail- Description
- Use when building or reviewing agency's frugal discipline (Spec 332) or multi-agent self-installer (Spec 333), or when you want the minimal-code "lazy senior dev" reflex as a reference. Ponytail is the upstream MIT skill agency redeveloped natively as `frugal`; this skill is the reference pointer — the engine implementation stays native (no vendored ponytail source).
- License
- MIT
- Instructions
- 54 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ponytail — the lazy-senior-dev minimal-code reference > *"He says nothing. He writes one line. It works."* Ponytail is the upstream > open-source skill (MIT, [DietrichGebert/ponytail](https://github.com/DietrichGebert/ponytail)) > that agency **redeveloped natively** as the `frugal` core discipline (Spec 332) > and the multi-agent self-installer (Spec 333). This skill is the **reference**, > not a re-vendoring: agency's core stays native (`agency/_frugal.py`), and > ponytail's name/source was deliberately removed from the engine (commit > `ec98a87`). Reach for the reference; never copy its source back into the engine. ## When to use - Building or reviewing **Spec 332** (frugal core discipline — `agency/_frugal.py`) or **Spec 333** (multi-agent installer — `install.surface_card` + adapters). - You want the minimal-code reflex itself: *write only what the task needs.* ## The discipline (the canon agency renders from `_frugal.py`) **Lazy means efficient, not careless. The best code is the code never written.** Before writing any code, stop at the **first rung that holds**: 1. Does this need to exist at all? (YAGNI) 2. Stdlib already does it? Use it. 3. Native platform feature covers it? Use it (`<input type="date">` over a picker lib). 4. Already-installed dependency solves it? Use it — never add one for a few lines. 5. Can it be one line? One line. 6. Only then: the minimum code that works. **The safety floor — never simplified away** (the substrings the drift + gate tests pin, `agency/_frugal.py:SAFETY_FLOOR_MARKERS`): input validation at trust boundaries · error handling that prevents data loss · security · accessibility · anything explicitly requested. *Frugal code without its check is unfinished* — non-trivial logic leaves ONE runnable check behind. **Marker convention:** deliberate simplifications get a `# frugal:` comment naming the ceiling + upgrade path (ponytail's `ponytail:` → agency's `# frugal:`). ## Where the reference lives (durable, in-repo) - `Plan/done/332-frugal-core-discipline/reference/DISCIPLINE.md` — the discipline design. - `Plan/done/333-multi-agent-installer/reference/INSTALLER.md` — the installer design (one source → many agents' native formats: `.cursor/rules/`, `.windsurf/rules/`, `.clinerules/`, `.kiro/steering/`, `AGENTS.md`, `.github/copilot-instructions.md`). - Upstream (full source, 14-agent installer, benchmarks): the GitHub repo above — clone it as scratch reference; do not commit its source into agency. ## The rule (why this is a pointer, not a port) Agency implements the discipline **from first principles** as a core feature with agency-native mechanism — the M2 per-verb envelope stamp (`prefix.frugal`) and the M1 hook injection have no upstream analogue; they exist because agency has a wire envelope and a hook layer. Study ponytail for the *pattern*; ship agency's own.
From netzkontrast/agency, MIT.
More from netzkontrast/agency
- 0.479score
loop-library
netzkontrast
Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions…
SkillCFreshness: CClaude Code +9 - 0.474score
silent-fail-recovery
netzkontrast
Deterministic recovery for Jules sessions that reach COMPLETED state without producing a remote branch (the "silent-fail" bug).
SkillCFreshness: CClaude Code +9 - 0.474score
context-safe-patch-handling
netzkontrast
Never echo a Jules patch body into the orchestrator's context — always route through `tools/jules-patch-extract.py` which writes the patch to…
SkillCFreshness: CClaude Code +9 - 0.474score
jules-orchestrator-discipline
netzkontrast
Six hard-won orchestrator rules for dispatching, watching, and harvesting Google Jules sessions — derived from the 2026-05-17 silent-fail incidents.
SkillCFreshness: CClaude Code +9 - 0.471score
jules-orchestrator
netzkontrast
Delegates long-running codebase tasks (refactors, multi-file edits, test generation, feature implementation, automated PR creation) to the Google Jules…
SkillCFreshness: CClaude Code +9 - 0.471score
orchestrate
netzkontrast
Run a Jules session through its full lifecycle — dispatch, plan approval, monitor, verify, integrate — driven by the jules-row state machine.
SkillCFreshness: CClaude Code +9 - 0.469score
research
netzkontrast
Research a topic and return findings as a tool-result envelope.
SkillCFreshness: CClaude Code +9 - 0.469score
recover
netzkontrast
Recover a silent-failed Jules session — extract its patch metadata into the ontology and (optionally) apply it locally.
SkillCFreshness: CClaude Code +9 - 0.467score
music-clipboard
netzkontrast
Copies track content (lyrics, style prompts, streaming lyrics) to the system clipboard.
SkillCFreshness: CClaude Code +9 - 0.467score
music-document-hunter
netzkontrast
Searches and retrieves documents from free public sources using automated browser navigation.
SkillCFreshness: CClaude Code +9 - 0.467score
music-cloud-uploader
netzkontrast
Uploads promo videos and content to Cloudflare R2 or AWS S3.
SkillCFreshness: CClaude Code +9 - 0.467score
music-album-conceptualizer
netzkontrast
Designs album concepts, tracklist architecture, and thematic planning through 7 structured phases.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 21, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/netzkontrast/agency
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from netzkontrast
- 0.479score
loop-library
netzkontrast
Discover, find, compare, audit, repair, adapt, and design repeatable AI-agent loops with explicit triggers, actions, verification, stopping conditions…
SkillCFreshness: CClaude Code +9 - 0.474score
silent-fail-recovery
netzkontrast
Deterministic recovery for Jules sessions that reach COMPLETED state without producing a remote branch (the "silent-fail" bug).
SkillCFreshness: CClaude Code +9 - 0.474score
jules-orchestrator-discipline
netzkontrast
Six hard-won orchestrator rules for dispatching, watching, and harvesting Google Jules sessions — derived from the 2026-05-17 silent-fail incidents.
SkillCFreshness: CClaude Code +9 - 0.474score
context-safe-patch-handling
netzkontrast
Never echo a Jules patch body into the orchestrator's context — always route through `tools/jules-patch-extract.py` which writes the patch to…
SkillCFreshness: CClaude Code +9 - 0.471score
orchestrate
netzkontrast
Run a Jules session through its full lifecycle — dispatch, plan approval, monitor, verify, integrate — driven by the jules-row state machine.
SkillCFreshness: CClaude Code +9 - 0.471score
jules-orchestrator
netzkontrast
Delegates long-running codebase tasks (refactors, multi-file edits, test generation, feature implementation, automated PR creation) to the Google Jules…
SkillCFreshness: CClaude Code +9
Cite this page
ponytail skill. Agent Mart. https://agentmart.dev/skills/netzkontrast-ponytail (last updated 2026-10-24)